Helm charts for Distributed Edge Analytics.

Initial Helm charts for CollectD, Prometheus Operator,
Kafka Strimzi operator, Rook Ceph Operator.

Change-Id: I7323029bd0bf1e4b39aac329fc567f705a59bc0c
Issue-ID: ONAPARC-366
Signed-off-by: Dileep Ranganathan <dileep.ranganathan@intel.com>

1 files changed, 93 insertions, 0 deletions

diff --git a/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-resources.yaml b/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-resources.yaml
new file mode 100644
index 00000000..4a7b9f95
--- /dev/null
+++ b/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-resources.yaml
@@ -0,0 +1,93 @@
+# Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/coreos/prometheus-operator/master/contrib/kube-prometheus/manifests/prometheus-rules.yaml
+{{- if and .Values.defaultRules.create }}
+apiVersion: {{ printf "%s/v1" (.Values.prometheusOperator.crdApiGroup | default "monitoring.coreos.com") }}
+kind: PrometheusRule
+metadata:
+  name: {{ printf "%s-%s" (include "prometheus-operator.fullname" .) "kubernetes-resources" | trunc 63 | trimSuffix "-" }}
+  labels:
+    app: {{ template "prometheus-operator.name" . }}
+{{ include "prometheus-operator.labels" . | indent 4 }}
+{{- if .Values.defaultRules.labels }}
+{{ toYaml .Values.defaultRules.labels | indent 4 }}
+{{- end }}
+{{- if .Values.defaultRules.annotations }}
+  annotations:
+{{ toYaml .Values.defaultRules.annotations | indent 4 }}
+{{- end }}
+spec:
+  groups:
+  - name: kubernetes-resources
+    rules:
+    - alert: KubeCPUOvercommit
+      annotations:
+        message: Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
+      expr: |-
+        sum(namespace_name:kube_pod_container_resource_requests_cpu_cores:sum)
+          /
+        sum(node:node_num_cpu:sum)
+          >
+        (count(node:node_num_cpu:sum)-1) / count(node:node_num_cpu:sum)
+      for: 5m
+      labels:
+        severity: warning
+    - alert: KubeMemOvercommit
+      annotations:
+        message: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit
+      expr: |-
+        sum(namespace_name:kube_pod_container_resource_requests_memory_bytes:sum)
+          /
+        sum(node_memory_MemTotal_bytes)
+          >
+        (count(node:node_num_cpu:sum)-1)
+          /
+        count(node:node_num_cpu:sum)
+      for: 5m
+      labels:
+        severity: warning
+    - alert: KubeCPUOvercommit
+      annotations:
+        message: Cluster has overcommitted CPU resource requests for Namespaces.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
+      expr: |-
+        sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="requests.cpu"})
+          /
+        sum(node:node_num_cpu:sum)
+          > 1.5
+      for: 5m
+      labels:
+        severity: warning
+    - alert: KubeMemOvercommit
+      annotations:
+        message: Cluster has overcommitted memory resource requests for Namespaces.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit
+      expr: |-
+        sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="requests.memory"})
+          /
+        sum(node_memory_MemTotal_bytes{job="node-exporter"})
+          > 1.5
+      for: 5m
+      labels:
+        severity: warning
+    - alert: KubeQuotaExceeded
+      annotations:
+        message: Namespace {{`{{ $labels.namespace }}`}} is using {{`{{ printf "%0.0f" $value }}`}}% of its {{`{{ $labels.resource }}`}} quota.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded
+      expr: |-
+        100 * kube_resourcequota{job="kube-state-metrics", type="used"}
+          / ignoring(instance, job, type)
+        (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
+          > 90
+      for: 15m
+      labels:
+        severity: warning
+    - alert: CPUThrottlingHigh
+      annotations:
+        message: '{{`{{ printf "%0.0f" $value }}`}}% throttling of CPU in namespace {{`{{ $labels.namespace }}`}} for container {{`{{ $labels.container_name }}`}} in pod {{`{{ $labels.pod_name }}`}}.'
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
+      expr: "100 * sum(increase(container_cpu_cfs_throttled_periods_total{}[5m])) by (container_name, pod_name, namespace) \n  / \nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container_name, pod_name, namespace)\n  > 25"
+      for: 15m
+      labels:
+        severity: warning
+{{- end }}
\ No newline at end of file